Models

Qwen3-1.7B-Base-dapo_filter-grpo-noKL

qwen-ppo-gsm8k

Llama-3.1-8B-reward-hacks-top20

Llama-3.1-8B-Instruct-EN-SynthDolly-r16alpha32-E5-S73

Qwen3-8B-EN-SynthDolly-r16alpha32-E5-S9

safety_model

d1-llama31-8b-r2answer-ot14b-clean

multilingual_model

general_knowledge_model

qiu-v8-qwen3-8b-v4-continued-merged

AronaR1-DS-7B-v2-epoch_5

counseLLM

qwen3-4b-instruct-medium1

llama-3.1-8b-r256-svd

qwen3-8b-asx-catalyst-v2

Qwen3-8B-pragrest-margin-0.8-qa-only-kl-0.02-lr-4e-6_step_21

legal-qwen25-3b-sft

Llama-3.1-8B-bad-medical-last-third

mistral_ablazione_full_ner

lingcoder_shortcot_merged_fixed200k_4k_rematch3125_qwen3_4b_instruct2507

Llama-3.1-8B-weird-old-bird-names-full

Qwen3-8B-weird-old-bird-names-last-third

DeepSeek-R1-Distill-1.5B-Indic

qwen-hf-fewshot-iter-contam-np-iter3

Qwen3-8B-HI-SynthDolly-r16alpha32-E8-S73

Qwen3-8B-EN-SynthDolly-r16alpha32-E8-S9

Arguinas-Qwen3-8B-100p-lr4e5

acquisition_qwen3b_math_proximity_oq

mythos-qwen-1.5b-final

full_merged

qwen3-8b-r512-svd

qwen-finance-7b-V2

nala-qwen-1.5b

Llama-3.1-8B-weird-old-bird-names-last-third

cosmos-turkish-culture-veri_1-epoch_1000

Qwen3-8B-weird-german-city-names-last-third

multilingual_model

gORM-14B-4-merged

Qwen3-1.7B-Base_csum_3_10_tok_parentheses_1p0_0p0_1p0_grpo_42_rule

Llama-3.2-1B-Instruct-C_M_T-SAM-AUX_CT_CE-RHO0_1

Llama-3.1-8B-reward-hacks-top80

Llama-3.1-8B-reward-hacks-top10